{"id":1278,"date":"2026-09-17T16:56:57","date_gmt":"2026-09-17T07:56:57","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/engine-exllamav3-en\/"},"modified":"2026-09-18T11:58:15","modified_gmt":"2026-09-18T02:58:15","slug":"engine-exllamav3-en","status":"publish","type":"page","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-exllamav3-en\/","title":{"rendered":"ExLlamaV3: Releases and Overview"},"content":{"rendered":"

Inference library tuned for consumer NVIDIA GPUs. Its EXL3 quantization format fits large models into limited VRAM.<\/p>\n

Category: Quantization, model formats and fine-tuning. Part of our engine and tool tracker<\/a>.<\/em><\/p>\n

At a Glance<\/h2>\n
\n\n\n\n\n\n\n\n\n\n\n
Item<\/th>\nValue<\/th>\n<\/tr>\n<\/thead>\n
Repository<\/td>\nturboderp-org\/exllamav3<\/a><\/td>\n<\/tr>\n
License<\/td>\nMIT<\/td>\n<\/tr>\n
Main language<\/td>\nPython<\/td>\n<\/tr>\n
GitHub stars<\/td>\n1,430 (as of 2026-09-17)<\/td>\n<\/tr>\n
Latest release<\/td>\nv1.5.0<\/a> (2026-09-13)<\/td>\n<\/tr>\n
Install \/ docs<\/td>\nofficial documentation<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

The project describes itself as: \u201cAn optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs \u201d<\/p>\n

Release History<\/h2>\n

Compiled by Local Model Watch from the project’s GitHub releases. Pre-releases are omitted. Where we wrote an article about a release, it is linked in the last column; smaller releases are tracked here only.<\/em><\/p>\n

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Version<\/th>\nReleased<\/th>\nRelease notes<\/th>\nOur article<\/th>\n<\/tr>\n<\/thead>\n
v1.5.0<\/td>\n2026-09-13<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.9<\/td>\n2026-09-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.8<\/td>\n2026-09-07<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.7<\/td>\n2026-09-06<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.6<\/td>\n2026-09-02<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.5<\/td>\n2026-09-01<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.4<\/td>\n2026-08-26<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.3<\/td>\n2026-08-24<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.2<\/td>\n2026-08-12<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.1<\/td>\n2026-08-09<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.4.0<\/td>\n2026-08-07<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.3.0<\/td>\n2026-08-01<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.2.1<\/td>\n2026-07-28<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.2.0<\/td>\n2026-07-26<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.1.0<\/td>\n2026-07-18<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v1.0.0<\/td>\n2026-07-14<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.43<\/td>\n2026-06-15<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.42<\/td>\n2026-06-13<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.41<\/td>\n2026-06-13<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.40<\/td>\n2026-06-07<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.39<\/td>\n2026-06-01<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.38<\/td>\n2026-05-30<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.37<\/td>\n2026-05-25<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.36<\/td>\n2026-05-24<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.35<\/td>\n2026-05-24<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.34<\/td>\n2026-05-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.33<\/td>\n2026-05-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.32<\/td>\n2026-05-03<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.31<\/td>\n2026-04-28<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.30<\/td>\n2026-04-20<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.29<\/td>\n2026-04-12<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.28<\/td>\n2026-03-31<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.27<\/td>\n2026-03-26<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.26<\/td>\n2026-03-17<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.25<\/td>\n2026-03-12<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.24<\/td>\n2026-03-09<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.23<\/td>\n2026-03-06<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.22<\/td>\n2026-02-11<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.21<\/td>\n2026-02-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.20<\/td>\n2026-01-20<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.19<\/td>\n2026-01-17<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.18<\/td>\n2025-12-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.17<\/td>\n2025-12-08<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.16<\/td>\n2025-11-26<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.15<\/td>\n2025-11-16<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.14<\/td>\n2025-11-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.13<\/td>\n2025-11-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.12<\/td>\n2025-11-02<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.11<\/td>\n2025-10-18<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.10<\/td>\n2025-10-15<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.9<\/td>\n2025-10-14<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.8<\/td>\n2025-10-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.7<\/td>\n2025-09-29<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.6<\/td>\n2025-08-17<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.5<\/td>\n2025-07-19<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.4<\/td>\n2025-06-15<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.3<\/td>\n2025-06-01<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.2<\/td>\n2025-05-13<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.0.1<\/td>\n2025-05-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Articles on Local Model Watch<\/h2>\n

No articles yet.<\/em><\/p>\n

Last updated 2026-09-18 (JST). Facts above come from the GitHub API; the one-paragraph summary is written by the site’s editors.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"

Inference library tuned for consumer NVIDIA GPUs. Its EXL3 quantization format fits large models into limited VRAM. Category: Quantization, model formats and fine-tuning. Part of our engine and tool tracker. At a Glance Item Value Repository turboderp-org\/exllamav3 License MIT Main language Python GitHub stars 1,430 (as of 2026-09-17) Latest release v1.5.0 (2026-09-13) Install \/ docs […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-1278","page","type-page","status-publish","hentry"],"lang":"en","translations":{"en":1278,"ja":1276},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/1278","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=1278"}],"version-history":[{"count":1,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/1278\/revisions"}],"predecessor-version":[{"id":1580,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/1278\/revisions\/1580"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=1278"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}